A hybrid optimization algorithm‐based feature selection for thyroid disease classifier with rough type‐2 fuzzy support vector machine. Issue 1 (22nd September 2021)

• Record Type: Journal Article
• Authors: Sureshkumar, Vidhushavarshini; Balasubramaniam, Sathiyabhama; Ravi, Vinayakumar; Arunachalam, Ajay
• Is Part Of: Expert systems. Volume 39:Issue 1(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-09-22
• Subjects: classification -- clinical trial -- clustering algorithm -- feature selection -- fuzzy sets -- hormone -- machine learning -- optimization -- support vector machines -- thyroid disease; Expert systems (Computer science); 006.33
• DOI: 10.1111/exsy.12811
• Languages: English
• ISSNs: 0266-4720

Abstract

Abstract: Thyroid hormones are essential for all the metabolic and reproductive activities with significance to growth, and neuron development in the human body. The thyroid hormone dysfunction has many ill consequences, affecting the human population; thereby being a global epidemic. It is noticed that every one in 10 persons suffer from different thyroid disorders in India. In recent years, many researchers have implemented various disease predictive models based on Information and Communications Technology (ICT). Increasing the accuracy of disease classification is a critical and challenging task. To increase the accuracy of classification, in this paper, we propose a hybrid optimization algorithm‐based feature selection design for thyroid disease classifier with rough type‐2 fuzzy support vector machine. This work uses the hybrid optimization algorithm, which combines the firefly algorithm (FA) and butterfly optimization algorithm (BOA) to select the top‐n features. The proposed hybrid firefly butterfly optimization‐rough type‐2 fuzzy support vector machine (HFBO‐RT2FSVM) is evaluated with several key metrics such as specificity, accuracy, and sensitivity. We compare our approach with well‐known benchmark methods such as improved grey wolf optimization linear support vector machine (IGWO Linear SVM) and mixed‐kernel support vector machine (MKSVM) methods. From the experimental evaluations, we justify that our technique improves the accuracy by large thereby precise in identifying the thyroid disease. HFBO‐RT2FSVM model attained an accuracy of 99.28%, having specificity and sensitivity of 98 and 99.2%, respectively.